© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 7352
    Prev
    Next
    INDEX
    Explanations

    Please read

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron detects formatting or markup elements (e.g. HTML‐style tags and asterisk or bracket markers) in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <b>
    0.92
    <strong>
    0.83
    mathbf
    0.73
    jän
    0.70
    iu
    0.68
    pail
    0.64
    </td>
    0.63
    mysqli
    0.63
    iglie
    0.63
    boldsymbol
    0.62
    POSITIVE LOGITS
     WARNING
    1.09
    WARNING
    0.91
     warned
    0.77
    Warning
    0.76
     NOTE
    0.75
     Note
    0.73
     Warning
    0.70
     Сколько
    0.70
        
    0.68
     warning
    0.66
    Activations Density 0.006%

    No Known Activations